prop/config/runtime.exs

import Config

# config/runtime.exs is executed for all environments, including
# during releases. It is executed after compilation and before the
# system starts, so it is typically used to load production configuration
# and secrets from environment variables or elsewhere. Do not define
# any compile-time configuration in here, as it won't be applied.
# The block below contains prod specific runtime configuration.

# ## Using releases
#
# If you use `mix release`, you need to explicitly enable the server
# by passing the PHX_SERVER=true when you start it:
#
#     PHX_SERVER=true bin/microwaveprop start
#
# Alternatively, you can use `mix phx.gen.release` to generate a `bin/server`
# script that automatically sets the env var above.
alias Microwaveprop.Workers.CanadianSoundingFetchWorker
alias Oban.Plugins.Cron

if System.get_env("PHX_SERVER") do
  config :microwaveprop, MicrowavepropWeb.Endpoint, server: true
end

config :microwaveprop, MicrowavepropWeb.Endpoint, http: [port: String.to_integer(System.get_env("PORT", "4000"))]

if prometheus_token = System.get_env("PROMETHEUS_AUTH_TOKEN") do
  config :microwaveprop, :prometheus_auth_token, prometheus_token
end

if qrz_username = System.get_env("QRZ_USERNAME") do
  config :microwaveprop, Microwaveprop.Qrz.Client,
    username: qrz_username,
    password: System.get_env("QRZ_PASSWORD") || raise("QRZ_PASSWORD missing"),
    agent: System.get_env("QRZ_AGENT", "microwaveprop/1.0")
end

if google_api_key = System.get_env("GOOGLE_API_KEY") do
  config :microwaveprop, Microwaveprop.Geocoder, api_key: google_api_key
end

if config_env() == :prod do
  database_url =
    System.get_env("DATABASE_URL") ||
      raise """
      environment variable DATABASE_URL is missing.
      For example: ecto://USER:PASS@HOST/DATABASE
      """

  maybe_ipv6 = if System.get_env("ECTO_IPV6") in ~w(true 1), do: [:inet6], else: []

  # The secret key base is used to sign/encrypt cookies and other secrets.
  # A default value is used in config/dev.exs and config/test.exs but you
  # want to use a different value for prod and you most likely don't want
  # to check this value into version control, so we use an environment
  # variable instead.
  secret_key_base =
    System.get_env("SECRET_KEY_BASE") ||
      raise """
      environment variable SECRET_KEY_BASE is missing.
      You can generate one by calling: mix phx.gen.secret
      """

  host = System.get_env("PHX_HOST") || "example.com"

  # ## SSL Support
  #
  # To get SSL working, you will need to add the `https` key
  # to your endpoint configuration:
  #
  #     config :microwaveprop, MicrowavepropWeb.Endpoint,
  #       https: [
  #         ...,
  #         port: 443,
  #         cipher_suite: :strong,
  #         keyfile: System.get_env("SOME_APP_SSL_KEY_PATH"),
  #         certfile: System.get_env("SOME_APP_SSL_CERT_PATH")
  #       ]
  #
  # The `cipher_suite` is set to `:strong` to support only the
  # latest and more secure SSL ciphers. This means old browsers
  # and clients may not be supported. You can set it to
  # `:compatible` for wider support.
  #
  # `:keyfile` and `:certfile` expect an absolute path to the key
  # and cert in disk or a relative path inside priv, for example
  # "priv/ssl/server.key". For all supported SSL configuration
  # options, see https://hexdocs.pm/plug/Plug.SSL.html#configure/1
  #
  # We also recommend setting `force_ssl` in your config/prod.exs,
  # ensuring no data is ever sent via http, always redirecting to https:
  #
  #     config :microwaveprop, MicrowavepropWeb.Endpoint,
  #       force_ssl: [hsts: true]
  #
  # Check `Plug.SSL` for all available options in `force_ssl`.

  # ## Configuring the mailer
  #
  # In production you need to configure the mailer to use a different adapter.
  # Here is an example configuration for Mailgun:
  #
  #     config :microwaveprop, Microwaveprop.Mailer,
  #       adapter: Swoosh.Adapters.Mailgun,
  # tls: :always + explicit tls_options is required — SMTP2GO's endpoint sits
  # behind a wildcard cert (*.smtp2go.com) so SNI is mandatory, and gen_smtp
  # won't set it without explicit server_name_indication. Without this, the
  # handshake fails with an "unexpected_message" TLS alert.
  email_server = System.get_env("EMAIL_SERVER")

  # Production Oban: live scoring, polling, and on-demand QSO enrichment.
  # Runs on the Oban Pro Smart engine so we can use global_limit / rate_limit
  # to protect rate-limited upstreams (Copernicus CDS in particular).
  #
  # PROP_ROLE controls which workloads this pod picks up:
  #   * "hot" (default) — full hot-path: web, crons, all queues.
  #   * "backfill" — no web server (unset PHX_SERVER), no crons, and only
  #     backfill-style queues. Intended for smaller nodes dedicated to
  #     catching up historical enrichment without competing with the
  #     hourly propagation grid chain.
  prop_role = System.get_env("PROP_ROLE", "hot")

  hot_only_queues = [
    # 1 slot per pod. Two concurrent forecast-hour steps in a single
    # pod stack HRRR grid + native duct grid + scored band map into
    # ~5-6 GiB RSS, hitting the 6 GiB limit and OOM-killing the pod
    # mid-chain. With 3 pods we still get 3-way parallel fan-out
    # cluster-wide, which is enough to finish the f00–f18 chain
    # comfortably inside the hourly interval. PropagationPruneWorker
    # shares this queue at a lower priority; if a prune job blocks
    # the grid chain briefly, the chain's unique window protects
    # the next hourly fire.
    propagation: 1,
    commercial: 1,
    solar: 1
  ]

  shared_queues = [
    # 1 slot per pod (3 cluster-wide). Any higher than this and the
    # ASOS backfill hammers IEM hard enough to get HTTP 429s, which
    # fill the retryable queue and thrash pod CPU without making
    # forward progress.
    weather: 1,
    gefs: 1,
    # :hrrr queue removed — per-QSO HRRR fetches flow through
    # hrrr_fetch_tasks and the Rust hrrr-point-worker (Phase 3 Stream C).
    terrain: 3,
    iemre: 3,
    # Historical backfill for pre-2014 contacts (pre-HRRR archive).
    # NARR is fetched anonymously from NCEI with no quota, no job
    # queue. Replaced the ERA5/CDS pipeline which never produced a
    # single row in prod. era5_cds_jobs table is kept for inspection
    # but its workers/client are gone. See
    # docs/plans/2026-04-15-merra2-historical-backfill.md.
    narr: 6,
    rtma: 2,
    backfill_enqueue: 1,
    admin: 1,
    nexrad: 2,
    radar: 2,
    ionosphere: 1,
    space_weather: 1,
    mechanism: 4,
    exports: 1,
    contact_import: 4
  ]

  # config/config.exs sets a base Oban config (queues + cron) that Config
  # deep-merges with runtime.exs. To actually drop the hot-path queues on
  # backfill pods we can't use `limit: 0` — Oban Pro's Smart engine
  # rejects it with "local_limit must be greater than 0". Instead override
  # each queue with `paused: true` (queue exists, processes nothing).
  paused_queue = [local_limit: 1, paused: true]

  disabled_hot_queues = [
    propagation: paused_queue,
    commercial: paused_queue,
    solar: paused_queue,
    enqueue: paused_queue
  ]

  oban_queues =
    case prop_role do
      "backfill" -> disabled_hot_queues ++ shared_queues
      _ -> hot_only_queues ++ shared_queues
    end

  cron_plugin =
    {Cron,
     crontab: [
       {"0 8 * * *", Microwaveprop.Workers.SolarIndexWorker},
       {"*/5 * * * *", Microwaveprop.Commercial.PollWorker},
       # Hourly at :05. With scores written as binary files (not
       # Postgres) and HRRR grid profile persistence removed, a
       # full f00-f18 chain runs in ~45-60 min, so hourly fits.
       # If one chain slips past 60 min the :propagation queue's
       # concurrency-of-2 lets the next chain interleave; files
       # are keyed by (band, valid_time) so last-writer-wins gives
       # newer analysis data naturally.
       {"5 * * * *", Microwaveprop.Workers.PropagationGridWorker},
       # GEFS runs publish ~3-4h after the 00/06/12/18Z cycle; seed the
       # Day 2-7 outlook 5h after each run to stay safely past NOMADS'
       # publication lag. Seeder enqueues f024-f168 at 6-hour cadence
       # (25 jobs per run, 100/day) into the :gefs queue.
       {"30 5,11,17,23 * * *", Microwaveprop.Workers.GefsFetchWorker},
       {"*/15 * * * *", Microwaveprop.Workers.PropagationPruneWorker},
       # The :narr type is virtual: it targets contacts with hrrr_status =
       # :unavailable (pre-2014, missing from the HRRR archive) and dispatches
       # NarrFetchWorker against NCEI. See narr_jobs_for_contact/1.
       {"*/30 * * * *", Microwaveprop.Workers.BackfillEnqueueWorker,
        args: %{"types" => ["hrrr", "weather", "terrain", "iemre", "narr", "radar", "mechanism"]}},
       # Hourly safety net for pos1/pos2/distance_km. Normally every contact
       # gets positions at insert time via Radio.resolve_grids_and_insert/1,
       # but direct DB writes (manual fixes, bulk imports) can bypass that.
       {"0 * * * *", Microwaveprop.Workers.ContactPositionBackfillWorker, args: %{"limit" => 500}},
       # UWYO publishes the 00Z/12Z Canadian radiosondes ~90 minutes after launch
       {"30 1 * * *", CanadianSoundingFetchWorker},
       {"30 13 * * *", CanadianSoundingFetchWorker},
       # GIRO DIDBase publishes foF2/foEs/hmF2 at ~7.5 min cadence; poll
       # every 10 min per station (Millstone Hill, Alpena) for the 144
       # MHz sporadic-E and HF MUF scoring inputs.
       {"*/10 * * * *", Microwaveprop.Workers.IonosphereFetchWorker},
       # NOAA SWPC: Kp / GOES X-ray at 1-min cadence, F10.7 hourly.
       # 5-min poll balances freshness vs request volume.
       {"*/5 * * * *", Microwaveprop.Workers.SpaceWeatherFetchWorker}
     ]}

  base_plugins = [
    {Oban.Plugins.Pruner, max_age: 3600 * 24},
    # DynamicLifeline uses producer records (heartbeats from each
    # live node) to rescue orphans, not a timer. When a pod dies
    # mid-deploy its Producer row disappears and any in-flight job
    # with that producer in `attempted_by` gets moved back to
    # `available` on the next rescue cycle — within ~30s instead of
    # waiting for a timer-based `rescue_after` to expire. Critical
    # for PropagationGridWorker chain steps to recover from rolling
    # deploys before the next hourly cron fire.
    {Oban.Pro.Plugins.DynamicLifeline, rescue_interval: to_timeout(second: 30)}
  ]

  # Backfill pods must not fire the hourly cron. Config deep-merge by
  # module key means we can't just omit the Cron plugin — config.exs
  # registers it and that registration survives. Override it with an
  # empty crontab on backfill pods so the plugin exists but schedules
  # nothing.
  empty_cron_plugin = {Cron, crontab: []}

  oban_plugins =
    case prop_role do
      "backfill" -> base_plugins ++ [empty_cron_plugin]
      _ -> base_plugins ++ [cron_plugin]
    end

  config :libcluster,
    topologies: [
      k8s: [
        strategy: Cluster.Strategy.Kubernetes,
        config: [
          mode: :ip,
          kubernetes_ip_lookup_mode: :pods,
          kubernetes_node_basename: "microwaveprop",
          kubernetes_selector: "app=prop",
          kubernetes_namespace: "prop"
        ]
      ]
    ]

  config :microwaveprop, Microwaveprop.Mailer,
    adapter: Swoosh.Adapters.SMTP,
    relay: email_server,
    port: 587,
    username: System.get_env("EMAIL_USERNAME"),
    password: System.get_env("EMAIL_PASSWORD"),
    tls: :always,
    tls_options: [
      server_name_indication: String.to_charlist(email_server || ""),
      versions: [:"tlsv1.2", :"tlsv1.3"],
      verify: :verify_none
    ],
    auth: :always

  config :microwaveprop, Microwaveprop.Repo,
    # ssl: true,
    url: database_url,
    pool_size: String.to_integer(System.get_env("POOL_SIZE") || "20"),
    # For machines with several cores, consider starting multiple pools of `pool_size`
    # pool_count: 4,
    socket_options: maybe_ipv6

  config :microwaveprop, MicrowavepropWeb.Endpoint,
    # SSL terminated by Cloudflare tunnel; generated URLs still use https
    url: [host: host, port: 443, scheme: "https"],
    http: [
      # Enable IPv6 and bind on all interfaces.
      # Set it to  {0, 0, 0, 0, 0, 0, 0, 1} for local network only access.
      # See the documentation on https://hexdocs.pm/bandit/Bandit.html#t:options/0
      # for details about using IPv6 vs IPv4 and loopback vs public addresses.
      ip: {0, 0, 0, 0, 0, 0, 0, 0}
    ],
    secret_key_base: secret_key_base

  config :microwaveprop, Oban,
    engine: Oban.Pro.Engines.Smart,
    queues: oban_queues

  config :microwaveprop, Oban, plugins: oban_plugins
  config :microwaveprop, :email_from, {"NTMS Propagation", "prop@w5isp.com"}
  config :microwaveprop, hrrr_base_url: System.get_env("HRRR_BASE_URL", "http://skippy.w5isp.com:8080")
  config :microwaveprop, srtm_tiles_dir: "/data/srtm"
  # config :microwaveprop, start_freshness_monitor: true
  config :microwaveprop, start_freshness_monitor: false
end